/
scraper.py
212 lines (151 loc) · 8.66 KB
/
scraper.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
import scraperwiki
import mechanize
import re
import csv
import time
from datetime import datetime, date
import datetime
#------------------------------------------------------------------------
#Load Prices from shareprices.com
#------------------------------------------------------------------------
#
if 1==0:
url = 'http://www.shareprices.com/ftseallshare'
br = mechanize.Browser()
# sometimes the server is sensitive to this information
br.addheaders = [('User-agent', 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.1) Gecko/2008071615 Fedora/3.0.1-1.fc9 Firefox/3.0.1')]
scraperwiki.sqlite.execute("drop table if exists company")
scraperwiki.sqlite.execute("create table company (`TIDM` string, `Company` string, `Price` real, `Volume` real, `Date` date NOT NULL)")
#scraperwiki.sqlite.execute("delete from company")
#scraperwiki.sqlite.commit()
response = br.open(url)
for pagenum in range(1):
html = response.read()
test1 = re.search(r'Day\'s Volume(.*?)<br \/><\/div>', html).group()
tuples = re.findall(r'(\">|\'>)(.*?)<\/', str(test1.replace(" ", "")).replace("><", ""))
count = 0
tidm = ""
company = ""
price = 0
poscnt = 0
for tuple in tuples:
if poscnt == 1:
company = tuple[1].replace("amp;", "")
if poscnt == 2:
price = tuple[1].replace(",", "").replace("p", "")
if poscnt == 4:
scraperwiki.sqlite.save(["TIDM"], data={"TIDM":tidm+'.L', "Company":company, "Price":price, "Volume":tuple[1].replace(",", ""), "Date":datetime.date.today()}, table_name='company')
scraperwiki.sqlite.commit()
if len(tuple[1]) <= 4 and tuple[1][-1:].isalpha() and tuple[1][-1:].isupper() and tuple[1]!=tidm and poscnt!=1:
count = count+1
tidm = tuple[1]
poscnt = 1
else:
poscnt = poscnt + 1
print "%s ftseallshare records were loaded" % (count)
#------------------------------------------------
#Load Signal History from British Bulls
#------------------------------------------------
if 1==1:
url = 'https://www.britishbulls.com/SignalPage.aspx?lang=en&Ticker='
#scraperwiki.sqlite.execute("drop table if exists Signal_History")
#scraperwiki.sqlite.execute("create table Signal_History (`TIDM` varchar2(8) NOT NULL, `Date` date NOT NULL, `Price` real NOT NULL, `Signal` varchar2(15) NOT NULL, `Confirmation` char(1) NOT NULL, `GBP 100` real NOT NULL, UNIQUE (`TIDM`, `Date`))")
lselist = scraperwiki.sqlite.execute("select `TIDM` from company where TIDM = 'FOUR.L'")
for x in lselist["data"]:
lsecode = str(x)[3:-2] #+ '.L'
br = mechanize.Browser()
# sometimes the server is sensitive to this information
br.addheaders = [('User-agent', 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.1) Gecko/2008071615 Fedora/3.0.1-1.fc9 Firefox/3.0.1')]
response = br.open(url + lsecode)
for pagenum in range(1):
html = response.read()
test1 = re.search(r'MainContent_signalpagehistory_PatternHistory24_DXDataRow0((.|\n)+)MainContent_signalpagehistory_PatternHistory24_IADD', html)
if test1:
test1 = test1.group(0)
test3 = re.findall('(\">|img\/)(.*?)(<\/|\.gif)', test1.replace("\B", ""))
while len(test3) >= 5:
sh_Date = re.search("(\w|\d)(.*)(\w|\d)", str(test3.pop(0)).replace(" ", "")).group(0)
sh_Date = date(int(sh_Date[6:10]),int(sh_Date[3:5]),int(sh_Date[:2]))
sh_Price = re.search("(\w|\d)(.*)(\w|\d)", str(test3.pop(0)).replace(" ", "").replace(",", "")).group(0)
sh_Signal = re.search("(\w|\d)(.*)(\w|\d)", str(test3.pop(0)).replace(" ", "")).group(0)
#print str(test3.pop(0)).replace(" ", "")
sh_Confirmation = ((re.search("[Uncheck|Check]", str(test3.pop(0)).replace(" ", "")).group(0).lower()).replace("img/uncheck","N")).replace("img/check", "Y")
sh_GBP100 = re.search("(\w|\d)(.*)(\w|\d)", str(test3.pop(0)).replace(" ", "").replace(",", "")).group(0)
print sh_Confirmation
#scraperwiki.sqlite.execute("insert or ignore into Signal_History values (?, ?, ?, ?, ?, ?)", [lsecode, sh_Date, sh_Price, sh_Signal, sh_Confirmation, sh_GBP100])
#scraperwiki.sqlite.commit()
#--------------------------------------------------
# Calculate Signal Performance
#--------------------------------------------------
if 1==0:
complist = scraperwiki.sqlite.execute("select `TIDM`, `Price`, `Date` from company where TIDM in (select distinct TIDM from Signal_History)")
#complist = scraperwiki.sqlite.execute("select `TIDM`, `Price`, `Date` from company where tidm = 'SIG.L'")
for x in complist["data"]:
tidm=x[0]
print tidm
nprice=x[1]
tdate=datetime.datetime.strptime(x[2], "%Y-%m-%d").date()
todaydate=datetime.date.today()
Commission=0.994
# Find Today GDP100
ldata = scraperwiki.sqlite.execute("select `Price` from Signal_History where tidm = '%s' and Date = '%s'" % (tidm, tdate))
if len(ldata["data"]) != 0:
for c in d1mindate["data"]:
tprice = c[0]
else:
ldata = scraperwiki.sqlite.execute("select `Date`, `GBP 100`, `Price`, `Signal` from Signal_History where tidm = '%s' and Date in (select max(`Date`) from Signal_History where tidm = '%s')" % (tidm, tidm))
if len(ldata["data"]) == 0:
tprice = 0
else:
for b in ldata["data"]:
LatestGDP100 = b[1]
LatestPrice = b[2]
LatestSignal = b[3]
ldiff = (nprice - LatestPrice) / LatestPrice
if LatestSignal == 'BUY':
tprice = (LatestGDP100 + (LatestGDP100*ldiff))*Commission
elif LatestSignal == 'SHORT':
tprice = (LatestGDP100 + (LatestGDP100*(ldiff*-1)))*Commission
#SELL etc
else:
tprice = LatestGDP100*.994
print "Latest: %s: $%s" % (tdate, round(tprice,2))
#------------------------------------------------------------
#D-1
d1date=todaydate - datetime.timedelta(days=10)
d1list = scraperwiki.sqlite.execute("select `GBP 100` from Signal_History where tidm = '%s' and Date = '%s'" % (tidm, d1date))
if len(d1list["data"]) != 0:
for a in d1list["data"]:
CalcPrice = a[0]
else:
d1mindate = scraperwiki.sqlite.execute("select `Date`, `GBP 100` from Signal_History where tidm = '%s' and Date in (select max(`Date`) from Signal_History where tidm = '%s' and Date < '%s')" % (tidm, tidm, d1date))
if len(d1mindate["data"]) == 0:
MinDate = '1900-01-01' #datetime.datetime.strptime(y[0], "%Y-%m-%d").date()
MinPrice = 0.0
else:
for y in d1mindate["data"]:
MinDate = datetime.datetime.strptime(y[0], "%Y-%m-%d").date()
MinPrice = y[1]
d1maxdate = scraperwiki.sqlite.execute("select `Date`, `GBP 100` from Signal_History where tidm = '%s' and Date in (select min(`Date`) from Signal_History where tidm = '%s' and Date > '%s')" % (tidm, tidm, d1date))
if len(d1maxdate["data"]) == 0:
MaxDate=tdate
MaxPrice=tprice
else:
for z in d1maxdate["data"]:
MaxDate = datetime.datetime.strptime(z[0], "%Y-%m-%d").date()
MaxPrice = z[1]
Abovedelta = MaxDate - d1date
Belowdelta = d1date - MinDate
MinMaxDelta = MaxDate - MinDate
PriceDelta = MaxPrice - MinPrice
if PriceDelta == 0:
PriceInterval=0
else:
PriceInterval = PriceDelta / MinMaxDelta.days
if abs(Abovedelta.days) >= Belowdelta.days:
CalcPrice = MinPrice+Belowdelta.days*PriceInterval
else:
CalcPrice = MaxPrice-Abovedelta.days*PriceInterval
D1PC = (tprice - CalcPrice) / CalcPrice
print "Latest - 10: %s: $%s %s" % (d1date, round(CalcPrice,2), round(D1PC*100,1))
print " "